Identification of incident required resolution time

Abstract

A system to provide end users with recommendations on improving the quality of the incident management process is provided. A computer device identifies a set of historical incident reports, wherein the historical incident reports identify: (i) incident tickets, (ii) one or more skills associated with personnel assigned to the incident tickets, and (iii) whether the incident tickets were resolved within threshold periods of time to resolve. The computing device trains a machine learning model to predict sets of skills associated with resolving incident tickets within the threshold periods of time to resolve based, at least in part, on the identified set of historical incident reports. The computing device assigns a set of personnel to the new incident ticket based, at least in part, on the predicted set of skills associated with resolving the new incident ticket within the threshold period of time to resolve.

What is claimed is: 
     
       1. A computer-implemented method, the method comprising:
 identifying, by one or more processors, historical data including a set of historical incident reports, wherein the historical incident reports identify: (i) incident tickets, (ii) one or more skills associated with personnel assigned to the incident tickets, and (iii) whether the incident tickets were resolved within threshold periods of time to resolve, the threshold periods of time to resolve including for a historical incident of the historical incident reports an anticipated resolution time and an actual resolution time for the historical incident, wherein the historical data further includes for the historical incident a set of personnel assigned to resolve the historical incident and the existing skillsets of the personnel assigned, the existing skillsets including the assigned personnel's existing range of skills, and wherein the identifying includes identifying, from the set of historical incident reports, anticipated ticket resolution times and corresponding actual ticket resolution times for a plurality of historical incident reports of the set of historical incident reports; 
 training, by one or more processors, a machine learning model to predict sets of skills associated with resolving incident tickets within the threshold periods of time to resolve, the training being based, at least in part, on the set of historical incident reports, the anticipated ticket resolution times and corresponding actual resolution times for the plurality of historical incident reports of the set of historical incident reports, and the existing skillsets of personnel assigned to the incident tickets in the identified historical data, including the assigned personnel's existing range of skills; 
 receiving a new incident ticket; 
 analyzing, by one or more processors, the new incident ticket and identifying a type of issue involved, a severity level of the issue, and a required resolution time for resolving the issue, wherein the required resolution time is associated with the severity level of the issue; 
 predicting, by one or more processors, using the trained machine learning model, a set of skills associated with resolving the new incident ticket within a threshold period of time to resolve, the predicting, using the trained machine learning model, being based, at least in part, on identifying the type of issue involved, the severity level of the issue, and the required resolution time for resolving the issue; and 
 assigning, by one or more processors using the machine learning model, a set of personnel to the new incident ticket based, at least in part, on the predicted set of skills associated with resolving the new incident ticket within the threshold period of time to resolve. 
 
     
     
       2. The computer-implemented method of  claim 1 , the method further comprising:
 generating, by the one or more processors, a new set of inputs for the machine learning model, wherein the new set of inputs includes: (i) the new incident ticket, (ii) the predicted set of skills associated with resolving the new incident ticket within the threshold period of time to resolve, and (iii) an indication of whether the new incident ticket was resolved within the threshold period of time to resolve; and 
 adjusting, by the one or more processors, the machine learning model based, at least in part, on the new set of inputs. 
 
     
     
       3. The computer-implemented method of  claim 1 , the method further comprising:
 normalizing, by the one or more processors, the anticipated ticket resolution times and the actual ticket resolution times; and 
 generating, by the one or more processors, a normalized incident profile chart (NIPC), wherein the normalized incident profile chart includes the normalized anticipated ticket resolution times and the normalized actual ticket resolution times. 
 
     
     
       4. The computer-implemented method of  claim 3 , the method further comprising:
 classifying, by the one or more processors, the incident tickets associated with the set of historical incident reports into categories based, at least in part, on respective locations of the respective tickets on the normalized incident profile chart. 
 
     
     
       5. The computer-implemented method of  claim 4 , wherein the categories include a miss category, wherein tickets in the miss category have actual ticket resolution times that exceed their respective anticipated ticket resolution times. 
     
     
       6. The computer-implemented method of  claim 5 , wherein the categories further include: (i) a no risk category, (ii) an automatic resolution/false alarm category, (iii) a fast response category, (iv) a good resources to volume match category, (v) a good skills to SLA match category, (vi) a skill or SLA issues category, and (vii) a resource or volume issue category. 
     
     
       7. A computer program product comprising:
 one or more computer-readable storage media and program instructions stored on the one or more computer-readable storage media, the stored program instructions comprising:
 program instructions to identify historical data including a set of historical incident reports, wherein the historical incident reports identify: (i) incident tickets, (ii) one or more skills associated with personnel assigned to the incident tickets, and (iii) whether the incident tickets were resolved within threshold periods of time to resolve, the threshold periods of time to resolve including for a historical incident of the historical incident reports an anticipated resolution time and an actual resolution time for the historical incident, wherein the historical data further includes for the historical incident a set of personnel assigned to resolve the historical incident and the existing skillsets of the personnel assigned, the existing skillsets including the assigned personnel's existing range of skills, and wherein the identifying includes identifying, from the set of historical incident reports, anticipated ticket resolution times and corresponding actual ticket resolution times for a plurality of historical incident reports of the set of historical incident reports; 
 program instructions to train a machine learning model to predict sets of skills associated with resolving incident tickets within the threshold periods of time to resolve, the training being based, at least in part, on the set of historical incident reports, the anticipated ticket resolution times and corresponding actual resolution times for the plurality of historical incident reports of the set of historical incident reports, and the existing skillsets of personnel assigned to the incident tickets in the identified historical data, including the assigned personnel's existing range of skills; 
 receiving a new incident ticket; 
 analyzing, by one or more processors, the new incident ticket and identifying a type of issue involved, a severity level of the issue, and a required resolution time for resolving the issue, wherein the required resolution time is associated with the severity level of the issue; 
 program instructions to predict using the trained machine learning model, a set of skills associated with resolving the new incident ticket within a threshold period of time to resolve, the predicting, using the trained machine learning model, being based, at least in part, on identifying the type of issue involved, the severity level of the issue, and the required resolution time for resolving the issue; and 
 program instructions to assign, using the machine learning model, a set of personnel to the new incident ticket based, at least in part, on the predicted set of skills associated with resolving the new incident ticket within the threshold period of time to resolve. 
 
 
     
     
       8. The computer program product of  claim 7 , the stored program instructions further comprising:
 program instructions to generate a new set of inputs for the machine learning model, wherein the new set of inputs includes: (i) the new incident ticket, (ii) the predicted set of skills associated with resolving the new incident ticket within the threshold period of time to resolve, and (iii) an indication of whether the new incident ticket was resolved within the threshold period of time to resolve; and 
 program instructions to adjust the machine learning model based, at least in part, on the new set of inputs. 
 
     
     
       9. The computer program product of  claim 7 , the stored program instructions further comprising:
 program instructions to normalize the anticipated ticket resolution times and the actual ticket resolution times; and 
 program instructions to generate a normalized incident profile chart (NIPC), wherein the normalized incident profile chart includes the normalized anticipated ticket resolution times and the normalized actual ticket resolution times. 
 
     
     
       10. The computer program product of  claim 9 , the stored program instructions further comprising:
 program instructions to classify the incident tickets associated with the set of historical incident reports into categories based, at least in part, on respective locations of the respective tickets on the normalized incident profile chart. 
 
     
     
       11. The computer program product of  claim 10 , wherein the categories include a miss category, wherein tickets in the miss category have actual ticket resolution times that exceed their respective anticipated ticket resolution times. 
     
     
       12. The computer program product of  claim 11 , wherein the categories further include: (i) a no risk category, (ii) an automatic resolution/false alarm category, (iii) a fast response category, (iv) a good resources to volume match category, (v) a good skills to SLA match category, (vi) a skill or SLA issues category, and (vii) a resource or volume issue category. 
     
     
       13. A computer system, the computer system comprising:
 one or more computer processors; 
 one or more computer readable storage medium; and 
 program instructions stored on the computer readable storage medium for execution by at least one of the one or more processors, the stored program instructions comprising:
 program instructions to identify historical data including a set of historical incident reports, wherein the historical incident reports identify: (i) incident tickets, (ii) one or more skills associated with personnel assigned to the incident tickets, and (iii) whether the incident tickets were resolved within threshold periods of time to resolve, the threshold periods of time to resolve including for a historical incident of the historical incident reports an anticipated resolution time and an actual resolution time for the historical incident, wherein the historical data further includes for the historical incident a set of personnel assigned to resolve the historical incident and the existing skillsets of the personnel assigned, the existing skillsets including the assigned personnel's existing range of skills, and wherein the identifying includes identifying, from the set of historical incident reports, anticipated ticket resolution times and corresponding actual ticket resolution times for a plurality of historical incident reports of the set of historical incident reports; 
 program instructions to train a machine learning model to predict sets of skills associated with resolving incident tickets within the threshold periods of time to resolve, the training being based, at least in part, on the set of historical incident reports, the anticipated ticket resolution times and corresponding actual resolution times for the plurality of historical incident reports of the set of historical incident reports, and the existing skillsets of personnel assigned to the incident tickets in the identified historical data, including the assigned personnel's existing range of skills; 
 receiving a new incident ticket; 
 analyzing, by one or more processors, the new incident ticket and identifying a type of issue involved, a severity level of the issue, and a required resolution time for resolving the issue, wherein the required resolution time is associated with the severity level of the issue; 
 program instructions to predict using the trained machine learning model, a set of skills associated with resolving the new incident ticket within a threshold period of time to resolve, the predicting, using the trained machine learning model, being based, at least in part, on identifying the type of issue involved, the severity level of the issue, and the required resolution time for resolving the issue; and 
 program instructions to assign, using the machine learning model, a set of personnel to the new incident ticket based, at least in part, on the predicted set of skills associated with resolving the new incident ticket within the threshold period of time to resolve. 
 
 
     
     
       14. The computer system of  claim 13 , the stored program instructions further comprising:
 program instructions to generate a new set of inputs for the machine learning model, wherein the new set of inputs includes: (i) the new incident ticket, (ii) the predicted set of skills associated with resolving the new incident ticket within the threshold period of time to resolve, and (iii) an indication of whether the new incident ticket was resolved within the threshold period of time to resolve; and 
 program instructions to adjust the machine learning model based, at least in part, on the new set of inputs. 
 
     
     
       15. The computer system of  claim 13 , the stored program instructions further comprising:
 program instructions to normalize the anticipated ticket resolution times and the actual ticket resolution times; and 
 program instructions to generate a normalized incident profile chart (NIPC), wherein the normalized incident profile chart includes the normalized anticipated ticket resolution times and the normalized actual ticket resolution times. 
 
     
     
       16. The computer system of  claim 15 , the stored program instructions further comprising:
 program instructions to classify the incident tickets associated with the set of historical incident reports into categories based, at least in part, on respective locations of the respective tickets on the normalized incident profile chart. 
 
     
     
       17. The computer system of  claim 16 , wherein the categories further include: (i) a no risk category, (ii) an automatic resolution/false alarm category, (iii) a fast response category, (iv) a good resources to volume match category, (v) a good skills to SLA match category, (vi) a skill or SLA issues category, and (vii) a resource or volume issue category.